SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2411.17835 · 2024

Arabic-Nougat: Fine-Tuning Vision Transformers for Arabic OCR and Markdown Extraction

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present Arabic-Nougat, a suite of OCR models for converting Arabic book pages into structured Markdown text. Based on Meta's Nougat architecture, Arabic-Nougat includes three specialized models: arabic-small-nougat, arabic-base-nougat, and arabic-large-nougat. These models are fine-tuned on a synthetic dataset, arabic-img2md, comprising 13.7k pairs of Arabic book pages and their Markdown representations. Key contributions include the Aranizer-PBE-86k tokenizer, designed for efficient tokenization, and the use of torch.bfloat16 precision with Flash Attention 2 for optimized training and inference. Our models achieve state-of-the-art performance, with arabic-large-nougat delivering the highest Markdown Structure Accuracy and the lowest Character Error Rate. Additionally, we release a large-scale dataset containing 1.1 billion Arabic tokens extracted from over 8,500 books using our best-performing model, providing a valuable resource for Arabic OCR research. All models, datasets, and code are open-sourced and available at https://github.com/MohamedAliRashad/arabic-nougat.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2411.17835")
get_code_for_paper("2411.17835")
have("2411.17835")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2411.17835.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2411.17835.svg)](https://syntology.ai/paper/2411.17835)

Connect an agent — have() is free.